---
title: "RAG on company documents: AI Knowledge Platform"
url: "https://www.sparkfabrik.com/en/solutions/ai-knowledge-platform/"
lang: "en"
type: "solution"
date: "2026-10-03"
lastmod: "2026-10-30"
description: "Your company's knowledge, queryable in natural language: governance per business unit, an open source stack, a swappable model and costs under control."
image: "https://www.sparkfabrik.com/images/og/soluzioni-ai-knowledge-platform-en.webp"
translations:
  it: "https://www.sparkfabrik.com/it/soluzioni/ai-knowledge-platform/index.md"
schema: {"@context":"https://schema.org","@id":"https://www.sparkfabrik.com/en/solutions/ai-knowledge-platform/#service","@type":"Service","areaServed":"Europe","description":"Your company's knowledge, queryable in natural language: governance per business unit, an open source stack, a swappable model and costs under control.","name":"AI Knowledge Platform","provider":{"@id":"https://www.sparkfabrik.com/#organization"},"serviceType":"AI Knowledge Platform","url":"https://www.sparkfabrik.com/en/solutions/ai-knowledge-platform/"}
---

# AI Knowledge Platform to query your company's documents.

People ask in natural language and get answers from the company's documents, with the source cited. **Every business unit has its own rules.**

[Tell us about your project](https://www.sparkfabrik.com/en/contact-us/)

- Multi-tenant per business unit
- Open source stack
- Data and inference in the EU
- No model lock-in

## Generic AI knows nothing about your company. And nobody governs it.

The AI Knowledge Platform is a company knowledge base with an AI assistant: it answers from internal documents and keeps the data, rules and costs of each business unit separate. SparkFabrik is an AI Native Engineering company that designs and runs AI assistants with guardrails for clients such as Luiss.

The knowledge is already there: manuals, data sheets, procedures, website pages, the documents of every business unit. But the people working on site, at the counter, in the classroom or on the phone have no time to look for it, and the questions always end up with the same experts.

Meanwhile every department tries its own AI tool: data leaving with no rules, costs nobody sees, invented answers that look true.

**One platform to bring AI to company knowledge, business unit by business unit, with clear rules, costs and responsibilities.**

Answers you can check

## Every answer has its source.

Every answer cites the document and the page, with a link to the original. **If the information is not in the documents, it says so** and points to the right person.

_Try the assistant: pick a question; the answer cites the document and the page, and the citation opens the passage of the manual. When the information is missing, the assistant says so and offers to write to the technical office._

Governance by business unit

## Every department, its own rules and budget.

Every business unit is a tenant: it decides what goes into its knowledge base, **which model to use** and who can access it. Requests, tokens and cost are visible per tenant, with an **automatic alert at 80%**.

_Try the governance: change the model of a business unit and simulate a week of requests; the budget is used according to the chosen model and at 80% its owner is alerted._

Extraction and indexing

## The documents you have become knowledge.

PDF, images, Word, Excel, PowerPoint and web pages, **uploaded by each team on its own**, with a reference to the source page.

_Try the indexing: add a sample document and watch it go from uploaded to extracted, split into passages and indexed, with a reference to its source page._

## The situations people start from.

You start from one concrete use case, then the same platform serves the other departments: sales, support, production, finance.

### Agents, installers and technicians keep calling the technical office

Answers come from the official documentation, even on the phone, with the link to the document and the page. The experts are left with the new cases.

### Every business unit has different documents, rules and budgets

Every business unit is a tenant: it decides what goes into its own knowledge base, which model to use, with which prompt and who can access it.

### Every department uses a different AI tool, with no common rules

A single access point to the models, with guardrails, spending caps and metrics per business unit. IT sets the rules, departments get on with their work.

### We are afraid model costs will get out of hand

Requests, tokens and cost are visible per tenant. The budget is daily, weekly or monthly, with an automatic alert at 80%.

### We cannot send our data just anywhere

Services and inference in European Union regions, personal data masked in the logs, GDPR roles written into the contract.

### The public website has to answer students, customers or citizens

The interface is an accessible web component: it goes into the website, the intranet or the e-learning platform, with anonymous access or through company SSO.

## How it works.

Five components developed by SparkFabrik on open source technologies, installed on cloud native infrastructure in the European Union.

1. **Conversational widget** (Interface): Streaming chat as an accessible web component, with cited sources and a link to the original document. Anonymous access or through SSO, OIDC or SAML.
2. **Multi-tenant back office** (Governance): On Drupal: tenants, content to index, prompts with history and rollback, a model per tenant, metrics and feedback.
3. **Agentic AI Gateway** (Engine): It decides whether to query the knowledge base, retrieves the context with RAG and builds the answer. If the sources are not enough, it points to the right contact.
4. **Proxy to the models** (Control): A single gateway to the model providers: spending caps and rate limits per tenant, guardrails, consumption metrics.
5. **Extraction and indexing** (Knowledge): PDF, images, Word, Excel, PowerPoint and web pages, uploaded by every team on its own, with the reference to the source page.

- Drupal, Go, Svelte, LiteLLM, Typesense, Firestore, Kubernetes, Infrastructure as Code, Gemini, Claude, OpenAI, Mistral

## A platform, not a chatbot.

These points set a demo apart from a system the company uses every day.

- **No lock-in, not even on the model**: Open source components and a single proxy to the models: the model is chosen per tenant and changed from the interface.
  - **Gemini, Claude, OpenAI, Mistral** or hosted models, depending on the use case.
  - **Code and configuration** under version control, infrastructure as code.
- **Inside a clear perimeter**: The system answers only from the indexed content, with guardrails against harmful content and manipulation.
  - **Inference in the EU**, consistent with the AI Act.
  - **De-identified logs** and written GDPR roles: the client is the controller, we are the processor.
  - **Certified processes** ISO/IEC 27001, 27017 and 27018.
- **From the first use case to the whole company**: You start from one department and a defined goal. The others join on the same platform, with the same rules.
  - **Sales, support, production, finance**: one tenant each.
  - **Evolution**: technical drawings and images, then the unwritten know-how of the experts, by voice too.

Success Stories

## In production.

The same components run Luiss's chatbot with guardrails and its conversational search.

- [Luiss](https://www.sparkfabrik.com/en/success-stories/luiss/), University: A chatbot with safe, controlled answers thanks to AI Guardrails, a conversational engine and agents, search anchored to the university's content.
- [Open source](https://www.sparkfabrik.com/en/services/drupal/drupal-certified-partner/), Drupal AI Initiative: AI Guardrails, MCP Client and the Typesense RAG recipe are Drupal modules we maintain.
- [Guide](https://www.sparkfabrik.com/en/landing/agenti-ai-processi-aziendali/), Whitepaper: The AI agents transforming business processes: architectures, use cases, governance.

The platform is in production or on its way at other companies, manufacturers included. We will name them when they are public.

## What is always included.

Everything else gets decided together.

- **The platform** (Five components): Widget, multi-tenant back office, AI Gateway, proxy to the models, indexing, on your cloud infrastructure or run by us.
  - Included: Agreed tenants, Guardrails, Source citation, Metrics, Budget, Feedback, Logs
  - Optional: More tenants, More models, CRM integrations, Ticketing or ERP
- **The knowledge** (Your documents, indexed): Extraction tuned on the document templates you point us to, indexing for RAG.
  - Included: The first indexing and the tuning on the agreed templates
  - Optional: New templates, Periodic re-indexing
- **The tuning** (Answers tested with users): Testing, user acceptance and tuning of the answers before go-live.
- **Running it** (After the release): Hosting, security, observability and platform updates.

## First a use case with a clear perimeter.

Then the platform grows, department after department.

1. **Text documentation**: PDF, Word and web pages become a queryable knowledge base, with source citation and the original document one click away. You leave with: The platform live for the first department.
2. **Visual technical content**: Images, technical drawings and diagrams enter the knowledge base. You leave with: Answers that also use what today only exists as a drawing.
3. **Unwritten knowledge**: The technical know-how that is not documented today: the expert explains, the system learns. By voice too. You leave with: The experts' know-how, available to everyone.

## How you pay.

- **Project build** (One-off): Analysis, implementation, integrations, indexing, testing and warranty.
- **Running fee** (Monthly): Platform, hosting, security and observability.
- **Model cost** (Pay per use): You pay for what you use, visible per tenant and with a cap.

## The phases of the first project.

- **Phase 1**: Detailed requirements
- **Phase 2**: Cloud infrastructure as code
- **Phase 3**: Document collection and indexing
- **Phase 4**: Development
- **Phase 5**: Testing, acceptance and tuning
- **Phase 6**: Go-live

**Watch it answer from your documents.** Bring us a handful of real documents and the questions you get most often. In a demo you see how it answers, with which sources, and what it says when it does not know. [Book a demo](https://www.sparkfabrik.com/en/contact-us/)

## The services inside this solution.

A solution is made of our services, put together for one precise problem.

- **AI Development**: The engine: RAG, agents, guardrails, integration with the models. ([more](https://www.sparkfabrik.com/en/services/ai-development/))
- **MCP servers**: To connect the platform to other company systems as tools, with permissions and audit. ([more](https://www.sparkfabrik.com/en/services/ai-development/))
- **Drupal**: The multi-tenant back office, with roles and approval workflows. ([more](https://www.sparkfabrik.com/en/services/drupal/))
- **Managed Services**: Running, updates and security of the platform after the release. ([more](https://www.sparkfabrik.com/en/services/cloud-native-services/managed-services/))
- **Kubernetes consulting**: The cloud native infrastructure it runs on. ([more](https://www.sparkfabrik.com/en/services/cloud-native-services/kubernetes-consultancy/))

**Your data stays where you decide.** Your documents stay within the perimeter you set: inference in European Union regions, and the **AI Guardrails** we maintain between the data and the model. (Open source: [AI Guardrails on drupal.org](https://www.drupal.org/project/ai_guardrails)) [The method: AI Native Engineering](https://www.sparkfabrik.com/en/ai-native-engineering/)

## Frequently asked questions.

The questions you are already asking.

### How is it different from a chatbot?

A chatbot is an interface. The AI Knowledge Platform is the system behind it: a knowledge base per business unit, model governance, budgets, guardrails, metrics and logs. The assistant is one of the ways to use it.

### Do you use AI on our projects? With what guarantees?

Yes. We build the platform with the same method as all our projects: specification, tests and review, and a person who approves every release. Inference in European Union regions, guardrails between the documents and the model, and a model you change from the interface: data stays within the perimeter you set.

### Does it make answers up?

No. It answers only with the context retrieved from the indexed content, citing document and page. If the information is not there, it gives a courtesy answer that points to the right contact.

### Which documents can it use?

PDF, images, Word documents, Excel sheets, PowerPoint presentations and web pages. Extraction is tuned on the most used document templates.

### Which model do you use?

The right one for the use case, for example Gemini, Claude, OpenAI or Mistral. Every business unit can have its own, and you can switch between the configured models from the interface.

### Where does the data live?

Services and inference in European Union regions, consistent with the AI Act. The client remains the data controller, SparkFabrik is the data processor under the GDPR.

### Does it connect to our company login?

Yes. For every tenant you choose anonymous or authenticated access, through the company Identity Provider with the OIDC or SAML standards.

### What does it cost?

We do not publish a price list. The offer always keeps three items separate: the one-off build, the running fee and the pay-per-use model cost, with a budget per tenant.

### How long does it take?

It depends on the documents and integrations you start from. The duration is defined at the end of phase 1, with the detailed requirements; every later phase ends with a release you can check, up to go-live.

## The other solutions.

- Solution: [Semantic and agentic search](https://www.sparkfabrik.com/en/solutions/semantic-agentic-search/): Search by meaning across sites, portals and archives, anchored to the official content.
- Solution: [Multisite, multilingual CMS](https://www.sparkfabrik.com/en/solutions/content-management-system/): One Drupal for every site, brand and language, with independent editors and AI that helps the people who write.

## Talk to the CEO or the CTO.

Tell us which business units, which documents and which constraints you have. We will tell you which use case we would start from.

[Tell us about your project](https://www.sparkfabrik.com/en/contact-us/)

- CEO: Stefano Mainardi, [Book 30 minutes](https://calendar.app.google/5N7BejeB8h1HpkYs7)
- CTO: Paolo Mainardi, [Book 30 minutes](https://calendar.app.google/gwe2fWtNU1aL31JCA)

Updated October 30, 2026.

---

*This is the Markdown version of the page, to facilitate reading by AI and crawlers. Visit [https://www.sparkfabrik.com/en/solutions/ai-knowledge-platform/](https://www.sparkfabrik.com/en/solutions/ai-knowledge-platform/) for the full version with images and interactions.*